hussius

# Download Kallisto and sratools (the latter to be able to download from SRA)
wget https://github.com/pachterlab/kallisto/releases/download/v0.42.3/kallisto_mac-v0.42.3.tar.gz
tar zvxf kallisto_mac-v0.42.3.tar.gz 
wget http://ftp-trace.ncbi.nlm.nih.gov/sra/sdk/2.5.2/sratoolkit.2.5.2-mac64.tar.gz
tar zxvf sratoolkit.2.5.2-mac64.tar.gz

# Download and merge human cDNA and ncDNA files from Ensembl for the index.
wget ftp://ftp.ensembl.org/pub/current_fasta/homo_sapiens/cdna/Homo_sapiens.GRCh38.cdna.all.fa.gz
wget ftp://ftp.ensembl.org/pub/current_fasta/homo_sapiens/ncrna/Homo_sapiens.GRCh38.ncrna.fa.gz
cat Homo_sapiens.GRCh38.cdna.all.fa.gz Homo_sapiens.GRCh38.ncrna.fa.gz > Homo_sapiens.GRCh38.rna.fa.gz

hussius

import tensorflow as tf
import numpy as np
import math
#import pandas as pd
#import sys

input = np.array([[2.0, 1.0, 1.0, 2.0],
                 [-2.0, 1.0, -1.0, 2.0],
                 [0.0, 1.0, 0.0, 2.0],
                 [0.0, -1.0, 0.0, -2.0],

hussius

"""
* Converts images to GGB (grayscale)
* Creates subsets for training and validation
* Adds columns to indicate training or validation (useful for analysis of the deployed model)
* Adds rotated images to the dataset
* Creates comma-separated CSV file
* Creates zip archive
"""

import pandas as pd

hussius

1. Install appropriate version of the Tensorflow (Python) framework from https://www.tensorflow.org/versions/r0.12/get_started/os_setup.html

In my case (Mac OS X 10.11), I did: 

- Get the .whl file (this is more likely to work than a direct pip install) 
wget https://storage.googleapis.com/tensorflow/mac/cpu/tensorflow-0.11.0-py3-none-any.whl

- Install using non-Anaconda pip
/usr/local/bin/pip3 install tensorflow-0.11.0-py3-none-any.whl_

hussius

from pathlib import Path
import os
import sys

from fire import Fire
import numpy as np
import pandas as pd
from tqdm import tqdm

hussius

def read_single_cossmo_example(serialized_example, n_tissues=1, coord_sys='rna1'):
    """Decode a single COSSMO example
    
    coord_sys must be one of 'rna1' or 'dna0', if 'dna0' then an extra 'strand' field
    must exist in the tfrecord and is extracted.
    """

    assert coord_sys in ['dna0', 'rna1']

    context_features = {

hussius

# Installation (only needs to be done once)
source("http://bioconductor.org/biocLite.R")
biocLite("rhdf5")
install.packages("devtools") 
devtools::install_github("pachterlab/sleuth")

# Now load the package
library("sleuth")

# A function (borrowed from the Sleuth documentation) for connecting Ensembl transcript names to common gene names

hussius

library(tensorflow)

tf$reset_default_graph()

x_data <- runif(100, min=0, max=1)
y_data <- x_data * 0.1 + 0.3 + rnorm(n, mean=0, sd=0.025)

W <- tf$Variable(tf$random_uniform(shape(1L), -1.0, 1.0))
b <- tf$Variable(tf$zeros(shape(1L)))
y <- W * x_data + b

hussius

import sys
import gzip 

if len(sys.argv)<3:
    sys.exit("python sum_per_gene.py <cDNA FASTA file> <TPM table>")

ensg = {}

mapf = gzip.open(sys.argv[1])
ctr = 0

hussius

args = commandArgs(trailingOnly=TRUE)
path=args[1]
files=Sys.glob(paste0(path,"/*/abundance.tsv"))
#print(files)
merge_two <- function(x,y){
	  #print(dim(x))
	  if ("tpm" %in% colnames(x)){
	     x_ <- x[,c(1,5)]
	     }
	   else{